Wasserstein generative adversarial networks are minimax optimal distribution estimators
From MaRDI portal
Publication:6656615
DOI10.1214/24-aos2430MaRDI QIDQ6656615
Arthur Stephanovitch, Eddie Aamari, Clément Levrard
Publication date: 3 January 2025
Published in: The Annals of Statistics (Search for Journal in Brave)
Nonparametric estimation (62G05) Approximations to statistical distributions (nonasymptotic) (62E17)
Cites Work
- Unnamed Item
- Unnamed Item
- Manifold estimation and singular deconvolution under Hausdorff loss
- Nonasymptotic rates for manifold, tangent space and curvature estimation
- Measure estimation on manifolds: an optimal transport approach
- Curvature Measures
- Mathematical Foundations of Infinite-Dimensional Statistical Models
- Orthonormal bases of compactly supported wavelets
- Two-Scale Difference Equations. I. Existence and Global Regularity of Solutions
- Integral Probability Metrics and Their Generating Classes of Functions
- Optimal Transport
- Introduction to nonparametric estimation
- On the approximation of functions by tanh neural networks
- Minimax rate of distribution estimation on unknown submanifolds under adversarial losses
- Neural Network Approximation of Refinable Functions
- Simultaneous approximation of a smooth function and its derivatives by deep neural networks with piecewise-polynomial activations
This page was built for publication: Wasserstein generative adversarial networks are minimax optimal distribution estimators
